Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/cortex-app/conduit/agents-mdgit clone --depth 1 https://github.com/cortex-app/conduitWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.02383 | $0.02383 |
| Opus 5 | $0.01192 | $0.01192 |
| Sonnet 5 | $0.00477 | $0.00477 |
| Haiku 4.5 | $0.00238 | $0.00238 |
Grade A, and why
conduit AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conduit MCP Server - AI Development Guide
Architecture Overview
Conduit is a Model Context Protocol (MCP) server that provides seamless integration with Phabricator and Phorge APIs through a modular client pattern with unified entry points.
Core Architecture
- Main Server (
src/conduit.py): FastMCP-based server with dual transport modes (stdio/HTTP-SSE) - Unified Client (
src/client/unified.py): Enhanced client with caching, retries, and token optimization - Modular Clients (
src/client/*.py): Specialized clients for different Phabricator APIs
Supported APIs
- Maniphest: Task management (search, create, edit tasks, get transaction history)
- Differential: Code review (search, create, manage revisions)
- Diffusion: Repository management (search, browse, commits, file content with base64 decoding)
- File: File management (search, upload, download)
- User: User management (information, queries)
- Project: Project management (search, members, workboards)
- Conduit: System interface (ping, capabilities, info)
Development Workflow
Environment Setup
This project uses uv virtual environment. Before executing any Python code, activate the Python virtual environment first:
# Since this is a Phabricator MCP Server, you may set environment variables
# Example environment variables (replace with your actual values):
# export PHABRICATOR_TOKEN="your-32-character-token"
# export PHABRICATOR_URL="https://your-phabricator-instance.com/api/"
# export PHABRICATOR_PROXY="socks5://127.0.0.1:1080" # Optional
# export PHABRICATOR_DISABLE_CERT_VERIFY=1 # Optional (security risk)
# Actual execution with environment variables:
PHABRICATOR_TOKEN="your-32-character-token" \
PHABRICATOR_URL="https://your-phabricator-instance.com/api/" \
PHABRICATOR_PROXY="socks5://127.0.0.1:1080" \
PHABRICATOR_DISABLE_CERT_VERIFY=1 \
source venv/bin/activate && python your_script.py
# Example, actual name may changed
source venv/bin/activate && uv pip xxx
source xxx && python xxx
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 256 lines · 2,383 tokens per session scan A e7b6d334516c
conduit AGENTS.md is an instructions file published in the GitHub repository cortex-app/conduit (7 stars, last pushed 7mo ago), licensed MIT. It adds 2,383 tokens to every session, about $0.0119 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.